Bonded Recourse for Smart-Contract Settlement of Compensable Agent Side Effects
Laurent Bindschaedler, Quentin Botha, Christoph Siebenbrunner
Abstract
Autonomous agent runtimes execute tool actions that mutate databases, repositories, and cloud services across organizational boundaries. Authorization and local compensation cover pre-action admission and in-runtime rollback, but neither settles the residual harm left after a permitted action fails. We design Recourse, a smart-contract settlement protocol for compensable agent side effects that binds each admitted action to scope, recovery, evidence, payout, and collateral. Recourse separates ex ante eligibility from ex post objective settleability: typed receipts make objective residual claims computable under an optimistic-oracle challenge pattern, while subjective or incomplete claims route to ERC-792 arbitration or exclusion. We implement the contract suite, deploy it on Base Sepolia, build adapters against Postgres, Git, and cloud-compatible local sandboxes, and evaluate the system on a deterministic harness, sandbox traces, adversarial sweeps, and property-based fuzzing. Against authorization-only and local-compensation baselines, bonded coverage cuts uncompensated harm. The on-chain tier supplies neutral custody, public challenge, non-cooperative payout, and portable history under cross-organizational trust assumptions.
Create a lesson
Related papers
Overcoming the Randomness-Utility Trade-off in Answering Differentially Private Linear Queries
Surendra Ghentiyala, Pritish Kamath, Ravi Kumar et al.
When Does Authorization End? Effect Closure at Provider Boundaries
Igor Santos-Grueiro
CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation
Varun Gadey, Ziad Marey, Alexandra Dmitrienko
SPADE: SPaT Attack Detection from the Connected Vehicle's Perspective
James Di Novo, Hany Ragab, Sylvain P. Leblanc
Card-Based Computation in the Virtual Player Simulation Model
Suthee Ruangwises
ACLE-MCP: Attested Capability Leases for Execution-Time Trust in Remote LLM Tool Use
Zhiyang Ding, Yang Luo, Guangpu Chen et al.